Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the readOnly and idempotent annotations, the description discloses that it skips specific categories (Uncategorized/Exclude/Internal Transfer, A2X/Stripe-clearing, pending rows, already posted rows) and that unmapped categories are listed, not dumped. This adds behavioral context about filtering and output handling that annotations alone do not provide.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured: it starts with a clear one-sentence summary, then gives exclusions trailing, then provides a workflow note and a routing example. Every sentence adds value (what it skips, how unmapped are handled, sequencing), with no filler or repetition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description gives a good sense of the tool's scope and behavior, including exclusions and placement in a workflow before post_xero_transaction. However, with no output schema, the description does not explicitly describe the return format (fields, structure) of the suggestions, leaving some ambiguity about what an agent receives from the call.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema description covers both parameters completely (companyId, limit with default and cap). The tool description adds no extra parameter-specific guidance; it does not elaborate on how limit affects suggestions or what companyId means beyond the schema. Baseline 3 applies because schema coverage is 100%.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states that the tool suggests FreedomOS bank transactions that are coded and ready to post into Xero as spend/receive money, with a specific verb and resource. It lists exclusions and distinguishes itself from posting tools by stating it is a pre-step, and from listing tools by focusing on rows ready to post.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly says 'Use before post_xero_transaction', providing a clear sequencing guideline. It also includes a natural language routing example ('What FO cash rows can we post to Xero? → suggest_xero_post') that tells an agent exactly when to invoke the tool. The list of skipped categories implicitly tells when not to expect results.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.